一种基于圈基的谱匹配算法

A spectral matching algorithm based on cycle basis

提出一种基于圈基的谱匹配算法.利用两幅待匹配图像的特征点分别构造一组圈基,根据圈基构造赋权邻接矩阵,并进行SVD分解,然后利用分解所得到的特征向量构造反映特征点之间匹配程度的关系矩阵和匹配概率矩阵,最后通过交替归一化将匹配概率矩阵转化为双随机矩阵的形式以获得匹配结果.模拟与真实图像实验结果均表明该方法具有可行性和有效性.

A spectral matching algorithm based on cycle basis was proposed in this paper. According to the feature points of two related images, two groups of cycle basis were found respectively. The weighted adjacent matrices were constructed from two groups of cycle basis respectively and singular-value decomposition （SVD） was performed to the matrices. Then, the matching matrix and initial probability matching matrix were completed from the result of SVD. Finally, the matching results were acquired by using doubly stochastic matrix. Experimental results demonstrated the feasibility and effectiveness of the approach.